filemap: add a kiocb_invalidate_post_direct_write helper

Add a helper to invalidate page cache after a dio write.

Link: https://lkml.kernel.org/r/20230601145904.1385409-7-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Anna Schumaker <anna@kernel.org>
Cc: Chao Yu <chao@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

fs/direct-io.c

@@ -285,14 +285,8 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
 	 * zeros from unwritten extents.
 	 */
 	if (flags & DIO_COMPLETE_INVALIDATE &&
-	    ret > 0 && dio_op == REQ_OP_WRITE &&
+	    ret > 0 && dio_op == REQ_OP_WRITE)
-	    dio->inode->i_mapping->nrpages) {
+		kiocb_invalidate_post_direct_write(dio->iocb, ret);
-		err = invalidate_inode_pages2_range(dio->inode->i_mapping,
-					offset >> PAGE_SHIFT,
-					(offset + ret - 1) >> PAGE_SHIFT);
-		if (err)
-			dio_warn_stale_pagecache(dio->iocb->ki_filp);
-	}
 
 	inode_dio_end(dio->inode);
 

fs/iomap/direct-io.c

@@ -81,7 +81,6 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	const struct iomap_dio_ops *dops = dio->dops;
 	struct kiocb *iocb = dio->iocb;
-	struct inode *inode = file_inode(iocb->ki_filp);
 	loff_t offset = iocb->ki_pos;
 	ssize_t ret = dio->error;
 
@@ -108,15 +107,8 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	 * ->end_io() when necessary, otherwise a racing buffer read would cache
 	 * zeros from unwritten extents.
 	 */
-	if (!dio->error && dio->size &&
+	if (!dio->error && dio->size && (dio->flags & IOMAP_DIO_WRITE))
-	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
+		kiocb_invalidate_post_direct_write(iocb, dio->size);
-		int err;
-		err = invalidate_inode_pages2_range(inode->i_mapping,
-				offset >> PAGE_SHIFT,
-				(offset + dio->size - 1) >> PAGE_SHIFT);
-		if (err)
-			dio_warn_stale_pagecache(iocb->ki_filp);
-	}
 
 	inode_dio_end(file_inode(iocb->ki_filp));
 

include/linux/fs.h

@@ -2843,11 +2843,6 @@ static inline void inode_dio_end(struct inode *inode)
 		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
 }
 
-/*
- * Warn about a page cache invalidation failure diring a direct I/O write.
- */
-void dio_warn_stale_pagecache(struct file *filp);
-
 extern void inode_set_flags(struct inode *inode, unsigned int flags,
 			    unsigned int mask);
 

include/linux/pagemap.h

@@ -31,6 +31,7 @@ int invalidate_inode_pages2(struct address_space *mapping);
 int invalidate_inode_pages2_range(struct address_space *mapping,
 		pgoff_t start, pgoff_t end);
 int kiocb_invalidate_pages(struct kiocb *iocb, size_t count);
+void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count);
 
 int write_inode_now(struct inode *, int sync);
 int filemap_fdatawrite(struct address_space *);

mm/filemap.c

@@ -3789,7 +3789,7 @@ EXPORT_SYMBOL(read_cache_page_gfp);
 /*
  * Warn about a page cache invalidation failure during a direct I/O write.
  */
-void dio_warn_stale_pagecache(struct file *filp)
+static void dio_warn_stale_pagecache(struct file *filp)
 {
 	static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST);
 	char pathname[128];
@@ -3806,19 +3806,23 @@ void dio_warn_stale_pagecache(struct file *filp)
 	}
 }
 
+void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count)
+{
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
+
+	if (mapping->nrpages &&
+	    invalidate_inode_pages2_range(mapping,
+			iocb->ki_pos >> PAGE_SHIFT,
+			(iocb->ki_pos + count - 1) >> PAGE_SHIFT))
+		dio_warn_stale_pagecache(iocb->ki_filp);
+}
+
 ssize_t
 generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 {
-	struct file	*file = iocb->ki_filp;
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
-	struct address_space *mapping = file->f_mapping;
+	size_t write_len = iov_iter_count(from);
-	struct inode	*inode = mapping->host;
+	ssize_t written;
-	loff_t		pos = iocb->ki_pos;
-	ssize_t		written;
-	size_t		write_len;
-	pgoff_t		end;
-
-	write_len = iov_iter_count(from);
-	end = (pos + write_len - 1) >> PAGE_SHIFT;
 
 	/*
 	 * If a page can not be invalidated, return 0 to fall back
@@ -3828,7 +3832,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	if (written) {
 		if (written == -EBUSY)
 			return 0;
-		goto out;
+		return written;
 	}
 
 	written = mapping->a_ops->direct_IO(iocb, from);
@@ -3850,11 +3854,11 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	 *
 	 * Skip invalidation for async writes or if mapping has no pages.
 	 */
-	if (written > 0 && mapping->nrpages &&
-	    invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end))
-		dio_warn_stale_pagecache(file);
-
 	if (written > 0) {
+		struct inode *inode = mapping->host;
+		loff_t pos = iocb->ki_pos;
+
+		kiocb_invalidate_post_direct_write(iocb, written);
 		pos += written;
 		write_len -= written;
 		if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
@@ -3865,7 +3869,6 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	}
 	if (written != -EIOCBQUEUED)
 		iov_iter_revert(from, write_len - iov_iter_count(from));
-out:
 	return written;
 }
 EXPORT_SYMBOL(generic_file_direct_write);